© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119744
    Prev
    Next
    INDEX
    Explanations

    foreign or diverse words reacting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     we
    -1.89
     these
    -1.44
     These
    -1.42
    </h3>
    -1.30
     had
    -1.27
    </h1>
    -1.27
     may
    -1.26
    These
    -1.26
     estas
    -1.19
     that
    -1.17
    POSITIVE LOGITS
     különböző
    1.57
     hemd
    1.46
     różnych
    1.42
     ยาว
    1.37
    capulco
    1.37
    mäh
    1.36
     oock
    1.34
    驁
    1.31
     steen
    1.30
     liknande
    1.30
    Activations Density 0.070%

    No Known Activations